Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to tokens that denote ownership or responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Bearer, Lesser", ferrous, boolean

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LogUtil
    -0.39
     locks
    -0.37
     manzana
    -0.35
     Squ
    -0.34
    umque
    -0.34
     StyleSheet
    -0.34
    Squ
    -0.34
     spé
    -0.33
    LogManager
    -0.33
     chanti
    -0.33
    POSITIVE LOGITS
    Bearer
    3.47
     Bearer
    2.33
    bearer
    2.09
     bearer
    1.99
     bearers
    1.55
    bearers
    1.52
    BEAR
    1.27
     BEAR
    1.16
     Bearing
    1.16
    Bearing
    1.13
    Act Density 0.002%

    No Known Activations